dc.contributor.author | Gauthier, Francois | |
dc.contributor.author | Gratton, Cristiano | |
dc.contributor.author | Dasanadoddi Venkategowda, Naveen Kumar | |
dc.contributor.author | Werner, Stefan | |
dc.date.accessioned | 2022-03-09T14:11:18Z | |
dc.date.available | 2022-03-09T14:11:18Z | |
dc.date.created | 2021-08-17T18:04:06Z | |
dc.date.issued | 2021 | |
dc.identifier.isbn | 978-1-6654-4707-2 | |
dc.identifier.uri | https://hdl.handle.net/11250/2984077 | |
dc.description.abstract | This paper develops a fully distributed differentially-private learning algorithm based on the alternating direction method of multipliers (ADMM) to solve nonsmooth optimization problems. We employ an approximation of the augmented Lagrangian to handle nonsmooth objective functions. Furthermore, we perturb the primal update at each agent with a time-varying Gaussian noise with decreasing variance to provide zero-concentrated differential privacy. The developed algorithm has competitive privacy-accuracy trade-off and applies to nonsmooth and non necessarily strongly convex problems. Convergence and privacy-preserving properties are confirmed via both theoretical analysis and simulations. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.relation.ispartof | The Fifty-Fourth Asilomar Conference on Signals, Systems & Computers | |
dc.title | Privacy-Preserving Distributed Learning with Nonsmooth Objective Functions | en_US |
dc.type | Chapter | en_US |
dc.description.version | acceptedVersion | en_US |
dc.rights.holder | © IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
dc.identifier.doi | 10.1109/IEEECONF51394.2020.9443287 | |
dc.identifier.cristin | 1926744 | |
dc.relation.project | Norges forskningsråd: 300102 | en_US |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |